{"id":"gpt-4o","slug":"gpt-4o","name":"GPT-4O","orgId":"openai","family":"gpt-4o","releaseDate":"2024-05-13","availability":"ga","openWeights":false,"license":"Proprietary","paramsTotal":null,"contextWindow":128000,"knowledgeCutoff":null,"modelCardUrl":"https://huggingface.co/datasets/lmarena-ai/leaderboard-dataset","hfRepo":null,"modalities":["text","speech","vision","image","file"],"aliases":["gpt-4o-2024-05-13","GPT-4O","gpt-4o-2024-08-06","gpt-4o-2024-11-20","GPT-4o (Mar 2025)","GPT-4o (Jan 2025)","GPT-4o (Nov 2024)","GPT-4o (Aug 2024)","openai/gpt-4o-2024-11-20","OpenAI: GPT-4o (2024-11-20)","openai/gpt-4o-2024-08-06","OpenAI: GPT-4o (2024-08-06)"],"aliasNote":null,"organization":{"id":"openai","name":"OpenAI","slug":"openai","country":null,"url":null,"color":"#10A37F","mark":"O"},"price":{"modelId":"gpt-4o","provider":"median of openai, openai, openai","inputPerM":null,"outputPerM":null,"blendedPerM":4.375000000000001,"tokensPerS":null,"observedAt":"2026-10-14","sourceId":"openrouter"},"answer":{"word":"It used to be.","scope":"Was SOTA in General LLM.","lead":"As of Oct 14, 2026, GPT-4O from OpenAI. Was SOTA in General LLM. Was SOTA in General LLM from 2024-08-28 to 2024-09-27.","confidence":"medium"},"verdicts":[{"id":"v_overall_general-llm_gpt-4o_2024-08-28_open_WAS_SOTA","model":"gpt-4o","model_name":"GPT-4O","category":"general-llm","category_name":"General LLM","slice":"overall","state":"WAS_SOTA","rank":null,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"medium","valid_from":"2024-08-28","valid_to":null,"configuration":null,"rationale":"Was SOTA in General LLM from 2024-08-28 to 2024-09-27.","safeguard_flags":["dethroned"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Was SOTA · General LLM"},{"id":"v_overall_reasoning_gpt-4o_2026-10-14_open_INSUFFICIENT_DATA","model":"gpt-4o","model_name":"GPT-4O","category":"reasoning","category_name":"Reasoning","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"lmarena-text-hard","name":"LMArena Text (style-controlled, hard prompts)","rank":11}],"missing_evidence":[{"benchmark":"hle","name":"Humanity's Last Exam"},{"benchmark":"gpqa-diamond","name":"GPQA Diamond"}],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"#11 on LMArena Text (style-controlled, hard prompts); missing Humanity's Last Exam and GPQA Diamond","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not enough data"},{"id":"v_overall_math_gpt-4o_2026-10-14_open_RANKED","model":"gpt-4o","model_name":"GPT-4O","category":"math","category_name":"Math","slice":"overall","state":"RANKED","rank":45,"present_evidence":[],"missing_evidence":[],"margin":100,"confidence":"medium","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Ranked #45 in Math.","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#45 in Math"},{"id":"v_overall_science_gpt-4o_2026-10-14_open_RANKED","model":"gpt-4o","model_name":"GPT-4O","category":"science","category_name":"Science","slice":"overall","state":"RANKED","rank":131,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Last listed at #131 in Science on 2024-11-20. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#131 in Science"},{"id":"v_overall_coding_gpt-4o_2026-10-14_open_INSUFFICIENT_DATA","model":"gpt-4o","model_name":"GPT-4O","category":"coding","category_name":"Coding","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"lmarena-text-coding","name":"LMArena Text (style-controlled, coding)","rank":10}],"missing_evidence":[{"benchmark":"terminal-bench-4","name":"Terminal-Bench 4.0"},{"benchmark":"swe-bench-pro-hard","name":"SWE-bench Pro V2 HARD"}],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"#10 on LMArena Text (style-controlled, coding); missing Terminal-Bench 4.0 and SWE-bench Pro V2 HARD","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not enough data"},{"id":"v_overall_long-context_gpt-4o_2026-10-14_open_INSUFFICIENT_DATA","model":"gpt-4o","model_name":"GPT-4O","category":"long-context","category_name":"Long context","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"lmarena-text-long","name":"LMArena Text (style-controlled, longer query)","rank":8}],"missing_evidence":[{"benchmark":"fictionlive-120k","name":"Fiction.liveBench 120k"}],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"#8 on LMArena Text (style-controlled, longer query); missing Fiction.liveBench 120k","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not enough data"},{"id":"v_overall_vision_gpt-4o_2026-10-14_open_INSUFFICIENT_DATA","model":"gpt-4o","model_name":"GPT-4O","category":"vision","category_name":"Vision","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"lmarena-vision","name":"LMArena Vision (style-controlled)","rank":80}],"missing_evidence":[{"benchmark":"gdp-pdf","name":"GDP.pdf"}],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"#80 on LMArena Vision (style-controlled); missing GDP.pdf","safeguard_flags":[],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not enough data"},{"id":"v_overall_factuality_gpt-4o_2026-10-14_open_INSUFFICIENT_DATA","model":"gpt-4o","model_name":"GPT-4O","category":"factuality","category_name":"Factuality","slice":"overall","state":"INSUFFICIENT_DATA","rank":null,"present_evidence":[{"benchmark":"simpleqa","name":"SimpleQA Verified","rank":61}],"missing_evidence":[{"benchmark":"lmarena-factuality","name":"LMArena Text factuality"}],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"#61 on SimpleQA Verified; missing LMArena Text factuality","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"Not enough data"},{"id":"v_overall_arc_gpt-4o_2026-10-14_open_RANKED","model":"gpt-4o","model_name":"GPT-4O","category":"arc","category_name":"Abstraction (ARC)","slice":"overall","state":"RANKED","rank":87,"present_evidence":[],"missing_evidence":[],"margin":null,"confidence":"low","valid_from":"2026-10-14","valid_to":null,"configuration":null,"rationale":"Last listed at #87 in Abstraction (ARC) on 2024-11-20. That board does not award a crown.","safeguard_flags":["off_board"],"co_sota_with":[],"challengers":[],"methodology":"1.0","label":"#87 in Abstraction (ARC)"}]}